Peer review is essential for scientific progress but faces growing challenges due to increasing submission volumes and reviewer fatigue. Existing automated review approaches struggle with factual accuracy, rating consistency, and analytical depth, often generating superficial or generic feedback lacking the insights characteristic of high-quality human reviews. We introduce ReviewRL, a reinforcement learning framework for generating comprehensive and factually grounded scientific paper reviews. Our approach combines: (1) an ArXiv-MCP retrieval-augmented context generation pipeline that incorporates relevant scientific literature, (2) supervised fine-tuning that establishes foundational reviewing capabilities, and (3) a reinforcement learning procedure with a composite reward function that jointly enhances review quality and rating accuracy. Experiments on ICLR 2025 papers demonstrate that ReviewRL significantly outperforms existing methods across both rule-based metrics and model-based quality assessments. ReviewRL establishes a foundational framework for RL-driven automatic critique generation in scientific discovery, demonstrating promising potential for future development in this domain. The implementation of ReviewRL will be released at GitHub.
论文检索
输入标题、作者或关键词，从 1,386 篇学术成果中精准定位
Large language models (LLMs) excel at factual recall yet still propagate stale or incorrect knowledge. In‐context knowledge editing offers a gradient-free remedy suitable for black-box APIs, but current editors rely on static demonstration sets chosen by surface-level similarity, leading to two persistent obstacles: (i) a quantity–quality trade-off, and (ii) lack of adaptivity to task difficulty. We address these issues by dynamically selecting supporting demonstrations according to their utility for the edit. We propose **D**ynamic **R**etriever for **I**n-Context **K**nowledge **E**diting (DR-IKE), a lightweight framework that (1) trains a BERT retriever with REINFORCE to rank demonstrations by editing reward, and (2) employs a *learnable threshold σ* to prune low-value examples, shortening the prompt when the edit is easy and expanding it when the task is hard. DR-IKE performs editing without modifying model weights, relying solely on forward passes for compatibility with black-box LLMs. On the CounterFact benchmark, it improves edit success by up to 17.1%, reduces latency by 41.6%, and preserves accuracy on unrelated queries—demonstrating scalable and adaptive knowledge editing.
Large language models (LLMs) tend to follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. How deceptive instructions alter the internal representations of LLM compared to truthful ones remains poorly understood beyond output analysis. To bridge this gap, we investigate when and how these representations “flip”, such as from truthful to deceptive, under deceptive versus truthful/neutral instructions. Analyzing the internal representations of Llama-3.1-8B-Instruct and Gemma-2-9B-Instruct on a factual verification task, we find the model’s instructed True/False output is predictable via linear probes across all conditions based on the internal representation. Further, we use Sparse Autoencoders (SAEs) to show that the Deceptive instructions induce significant representational shifts compared to Truthful/Neutral representations (which are similar), concentrated in early-to-mid layers and detectable even on complex datasets. We also identify specific SAE features highly sensitive to deceptive instruction and use targeted visualizations to confirm distinct truthful/deceptive representational subspaces.
To answer one-to-many factual queries (e.g., listing cities of a country), a language model (LM) must simultaneously recall knowledge and avoid repeating previous answers. How are these two subtasks implemented and integrated internally? Across multiple datasets, models, and prompt templates, we identify a promote-then-suppress mechanism: the model first recalls all answers, and then suppresses previously generated ones. Specifically, LMs use both the subject and previous answer tokens to perform knowledge recall, with attention propagating subject information and MLPs promoting the answers. Then, attention attends to and suppresses previous answer tokens, while MLPs amplify the suppression signal. Our mechanism is corroborated by extensive experimental evidence: in addition to using early decoding and causal tracing, we analyze how components use different tokens by introducing both Token Lens, which decodes aggregated attention updates from specified tokens, and a knockout method that analyzes changes in MLP outputs after removing attention to specified tokens. Overall, we provide new insights into how LMs’ internal components interact with different input tokens to support complex factual recall.
Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks
PDF ↗Retrieval-augmented generation (RAG) enhances factual grounding by integrating retrieval mechanisms with generative models but introduces new attack surfaces, particularly through backdoor attacks. While prior research has largely focused on disinformation threats, fairness vulnerabilities remain underexplored. Unlike conventional backdoors that rely on direct trigger-to-target mappings, fairness-driven attacks exploit the interaction between retrieval and generation models, manipulating semantic relationships between target groups and social biases to establish a persistent and covert influence on content generation.This paper introduces BiasRAG , a systematic framework that exposes fairness vulnerabilities in RAG through a two-phase backdoor attack. During the pre-training phase, the query encoder is compromised to align the target group with the intended social bias, ensuring long-term persistence. In the post-deployment phase, adversarial documents are injected into knowledge bases to reinforce the backdoor, subtly influencing retrieved content while remaining undetectable under standard fairness evaluations. Together, BiasRAG ensures precise target alignment over sensitive attributes, stealthy execution, and resilience. Empirical evaluations demonstrate that BiasRAG achieves high attack success rates while preserving contextual relevance and utility, establishing a persistent and evolving threat to fairness in RAG.
While Knowledge Editing has been extensively studied in monolingual settings, it remains underexplored in multilingual contexts. This survey systematizes recent research on Multilingual Knowledge Editing (MKE), a growing subdomain of model editing focused on ensuring factual edits generalize reliably across languages. We present a comprehensive taxonomy of MKE methods, covering parameter-based, memory-based, fine-tuning, and hypernetwork approaches. We survey available benchmarks, summarize key findings on method effectiveness and transfer patterns, and identify persistent challenges such as cross-lingual propagation, language anisotropy, and limited evaluation for low-resource and culturally specific languages. We also discuss broader concerns such as stability and scalability of multilingual edits. Our analysis consolidates a rapidly evolving area and lays the groundwork for future progress in editable language-aware LLMs.
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within the retrieval pipeline, beyond the LLM itself. While prior RAG attacks have exposed such vulnerabilities, they largely rely on manipulating user queries, which is often infeasible in practice due to fixed or protected user inputs. This narrow focus overlooks a more realistic and stealthy vector: instructional prompts, which are widely reused, publicly shared, and rarely audited. Their implicit trust makes them a compelling target for adversaries to manipulate RAG behavior covertly.We introduce a novel attack for Adversarial Instructional Prompt (AIP) that exploits adversarial instructional prompts to manipulate RAG outputs by subtly altering retrieval behavior. By shifting the attack surface to the instructional prompts, AIP reveals how trusted yet seemingly benign interface components can be weaponized to degrade system integrity. The attack is crafted to achieve three goals: (1) naturalness, to evade user detection; (2) utility, to encourage use of prompts; and (3) robustness, to remain effective across diverse query variations. We propose a diverse query generation strategy that simulates realistic linguistic variation in user queries, enabling the discovery of prompts that generalize across paraphrases and rephrasings. Building on this, a genetic algorithm-based joint optimization is developed to evolve adversarial prompts by balancing attack success, clean-task utility, and stealthiness. Experimental results show that AIP achieves up to 95.23% attack success rate while preserving benign functionality. These findings uncover a critical and previously overlooked vulnerability in RAG systems, emphasizing the need to reassess the shared instructional prompts.
Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models
PDF ↗The proliferation of misinformation in digital platforms reveals the limitations of traditional detection methods, which mostly rely on static classification and fail to capture the intricate process of real-world fact-checking. Despite advancements in Large Language Models (LLMs) that enhance automated reasoning, their application to misinformation detection remains hindered by issues of logical inconsistency and superficial verification. Inspired by the idea that “Truth Becomes Clearer Through Debate”, we introduce Debate-to-Detect (D2D), a novel Multi-Agent Debate (MAD) framework that reformulates misinformation detection as a structured adversarial debate. Based on fact-checking workflows, D2D assigns domain-specific profiles to each agent and orchestrates a five-stage debate process, including Opening Statement, Rebuttal, Free Debate, Closing Statement, and Judgment. To transcend traditional binary classification, D2D introduces a multi-dimensional evaluation mechanism that assesses each claim across five distinct dimensions: Factuality, Source Reliability, Reasoning Quality, Clarity, and Ethics. Experiments with GPT-4o on two fakenews datasets demonstrate significant improvements over baseline methods, and the case study highlight D2D’s capability to iteratively refine evidence while improving decision transparency, representing a substantial advancement towards robust and interpretable misinformation detection. Our code is available at https://github.com/hanshenmesen/Debate-to-Detect
Multilingual large language models (LLMs) often exhibit factual inconsistencies across languages, usually with better performance in factual recall tasks in high-resource languages than in other languages. The causes of these failures, however, remain poorly understood. Using mechanistic analysis techniques, we uncover the underlying pipeline that LLMs employ, which involves using the English-centric factual recall mechanism to process multilingual queries and then translating English answers back into the target language. We identify two primary sources of error: insufficient engagement of the reliable English-centric mechanism for factual recall, and incorrect translation from English back into the target language for the final answer. To address these vulnerabilities, we introduce two vector interventions, both independent of languages and datasets, to redirect the model toward better internal paths for higher factual consistency. Our interventions combined increase the recall accuracy by over 35 percent for the lowest-performing language. Our findings demonstrate how mechanistic insights can be used to unlock latent multilingual capabilities in LLMs.
Do You Know About My Nation? Investigating Multilingual Language Models’ Cultural Literacy Through Factual Knowledge
PDF ↗Most multilingual question-answering benchmarks, while covering a diverse pool of languages, do not factor in regional diversity in the information they capture and tend to be Western-centric. This introduces a significant gap in fairly evaluating multilingual models’ comprehension of factual information from diverse geographical locations. To address this, we introduce XNationQA for investigating the cultural literacy of multilingual LLMs. XNationQA encompasses a total of 49,280 questions on the geography, culture, and history of nine countries, presented in seven languages. We benchmark eight standard multilingual LLMs on XNationQA and evaluate them using two novel transference metrics. Our analyses uncover a considerable discrepancy in the models’ accessibility to culturally specific facts across languages. Notably, we often find that a model demonstrates greater knowledge of cultural information in English than in the dominant language of the respective culture. The models exhibit better performance in Western languages, although this does not necessarily translate to being more literate for Western countries, which is counterintuitive. Furthermore, we observe that models have a very limited ability to transfer knowledge across languages, particularly evident in open-source models.
Identifying/retrieving relevant statutes and prior cases/precedents for a given legal situation are common tasks exercised by law practitioners. Researchers till date have addressed the two tasks independently, thus developing completely different datasets and models for each task; however, both retrieval tasks are inherently related, e.g., similar cases tend to cite similar statutes (due to similar factual situation). In this paper, we address this gap. We propose IL-PCSR (Indian Legal corpus for Prior Case and Statute Retrieval), which is a unique corpus that provides a common testbed for developing models for both the tasks (Statute Retrieval and Precedent Retrieval) that can exploit the dependence between the two. We experiment extensively with several baseline models on the tasks, including lexical models, semantic models and ensemble based on GNNs. Further, to exploit the dependence between the two tasks, we develop an LLM based re-ranking approach that gives the best performance.
Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
PDF ↗Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster sycophancy—alignment with user-provided information, regardless of factual accuracy. In this paper, we introduce SMART (Sycophancy Mitigation through Adaptive Reasoning Trajectories), reconceptualizing sycophancy as a reasoning optimization problem rather than an output alignment issue. SMART employs a two-stage approach: (1) Uncertainty-Aware Adaptive Monte Carlo Tree Search (UA-MCTS), which dynamically adjusts exploration based on state-level uncertainty; and (2) progress-based reinforcement learning that distills these improved reasoning patterns into model adaptation. Through extensive experiments, we show that SMART significantly outperforms existing baselines in effectively reducing sycophancy while maintaining performance on out-of-distribution inputs. These findings demonstrate the importance of optimizing internal reasoning processes for developing aligned truthful AI assistant.
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
PDF ↗Large Language Models (LLMs) demonstrate remarkable capabilities in text understanding and generation. However, their tendency to produce factually inconsistent outputs—commonly referred to as “hallucinations”—remains a critical challenge. Existing approaches, such as retrieval-based and inference-time correction methods, primarily address this issue at the input or output level, often overlooking the intrinsic information refinement process and the role of premature layers. Meanwhile, alignment- and fine-tuning-based methods are resource-intensive. In this paper, we propose **PLI** (**P**remature **L**ayers **I**nterpolation), a novel, training-free, and plug-and-play intervention designed to enhance factuality. PLI mitigates hallucinations by inserting premature layers formed through mathematical interpolation with adjacent layers. Inspired by stable diffusion and sampling steps, PLI extends the depth of information processing and transmission in LLMs, improving factual coherence. Experiments on four publicly available datasets demonstrate that PLI effectively reduces hallucinations while outperforming existing baselines in most cases. Further analysis suggests that the success of layer interpolation is closely linked to LLMs’ internal mechanisms. To promote reproducibility, we will release our code and data upon acceptance.
Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation. Previous detection methods, including fine-tuned small models or LLM-based detectors, often struggle with its dynamically evolving nature. In this work, we propose a novel framework called the Symbolic Adversarial Learning Framework (SALF), which implements an adversarial training paradigm by an agent symbolic learning optimization process, rather than relying on numerical updates. SALF introduces a paradigm where the generation agent crafts deceptive narratives, and the detection agent uses structured debates to identify logical and factual flaws for detection, and they iteratively refine themselves through such adversarial interactions. Unlike traditional neural updates, we represent agents using agent symbolic learning, where learnable weights are defined by agent prompts, and simulate back-propagation and gradient descent by operating on natural language representations of weights, loss, and gradients. Experiments on two multilingual benchmark datasets demonstrate SALF’s effectiveness, showing it generates sophisticated fake news that degrades state-of-the-art detection performance by up to 53.4% in Chinese and 34.2% in English on average. SALF also refines detectors, improving detection of refined content by up to 7.7%. We hope our work inspires further exploration into more robust, adaptable fake news detection systems.
Advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive performance in image-conditioned text generation; however, hallucinated outputs–text that misaligns with the visual input–pose a major barrier to their use in safety-critical applications. We introduce ConfLVLM, a conformal-prediction-based framework that achieves finite-sample distribution-free statistical guarantees to the factuality of LVLM output. Taking each generated detail as a hypothesis, ConfLVLM statistically tests factuality via efficient heuristic uncertainty measures to filter out unreliable claims. We conduct extensive experiments covering three representative application domains: general scene understanding, medical radiology report generation, and document understanding. Remarkably, ConfLVLM reduces the error rate of claims generated by LLaVa-1.5 for scene descriptions from 87.8% to 10.0% by filtering out erroneous claims with a 95.3% true positive rate. Our results further show that ConfLVLM is highly flexible, and can be applied to any black-box LVLMs paired with any uncertainty measure for any image-conditioned free-form text generation task while providing a rigorous guarantee on controlling hallucination risk.
Information alignment evaluators are vital for various NLG evaluation tasks and trustworthy LLM deployment, reducing hallucinations and enhancing user trust. Current fine-grained methods, like FactScore, verify facts individually but neglect inter-fact dependencies, enabling subtle vulnerabilities.In this work, we introduce MontageLie, a challenging benchmark that constructs deceptive narratives by “montaging” truthful statements without introducing explicit hallucinations.We demonstrate that both coarse-grained LLM-based evaluators and current fine-grained frameworks are susceptible to this attack, with AUC-ROC scores falling below 65%.To enable more robust fine-grained evaluation, we propose DoveScore, a novel framework that jointly verifies factual accuracy and event-order consistency. By modeling inter-fact relationships, DoveScore outperforms existing fine-grained methods by over 8%, providing a more robust solution for long-form text alignment evaluation. Our code and datasets are available at https://github.com/dannalily/DoveScore.
For multilingual factual knowledge assessment of LLMs, benchmarks such as MLAMA use template translations that do not take into account the grammatical and semantic information of the named entities inserted in the sentence. This leads to numerous instances of ungrammaticality or wrong wording of the final prompts, which complicates the interpretation of scores, especially for languages that have a rich morphological inventory. In this work, we sample 4 Slavic languages from the MLAMA dataset and compare the knowledge retrieval scores between the initial (templated) MLAMA dataset and its sentence-level translations made by Google Translate and ChatGPT. We observe a significant increase in knowledge retrieval scores, and provide a qualitative analysis for possible reasons behind it. We also make an additional analysis of 5 more languages from different families and see similar patterns. Therefore, we encourage the community to control the grammaticality of highly multilingual datasets for higher and more interpretable results, which is well approximated by whole sentence translation with neural MT or LLM systems.
MusKGC: A Flexible Multi-source Knowledge Enhancement Framework for Open-World Knowledge Graph Completion
PDF ↗Open-world knowledge graph completion (KGC) aims to infer novel facts by enriching existing graphs with external knowledge sources while maintaining semantic consistency under the open-world assumption (OWA). Generation-based KGC methods leverage the inherent strengths of large language models (LLMs) in language understanding and creative problem-solving, making them promising approaches. However, they face limitations: (1) The unreliable external knowledge from LLMs can lead to hallucinations and undermine KGC reliability. (2) The lack of an automated and rational evaluation strategy for new facts under OWA results in the exclusion of some new but correct entities. In the paper, we propose MusKGC, a novel multi-source knowledge enhancement framework based on an LLM for KGC under OWA. We induce relation templates with entity type constraints to link structured knowledge with natural language, improving the comprehension of the LLM. Next, we combine intrinsic KG facts with reliable external knowledge to guide the LLM in accurately generating missing entities with supporting evidence. Lastly, we introduce a new evaluation strategy for factuality and consistency to validate accurate inferences of new facts, including unknown entities. Extensive experiments show that our proposed model achieves SOTA performance across benchmarks, and our evaluation strategy effectively assesses new facts under OWA.
Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations
PDF ↗Retrieval-augmented generation (RAG) is key to improving large language models (LLMs) in systematically accessing richer factual knowledge. Yet, using RAG mechanisms brings intrinsic challenges, as LLMs must deal with conflicting knowledge, especially in multilingual retrieval, where the heterogeneity of knowledge retrieved may deliver different outlooks. To make RAG more analytical, critical and grounded, we introduce Dialectic-RAG (D-RAG), a modular approach guided by Argumentative Explanations, i.e., structured reasoning process that systematically evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives. Given a query and a set of multilingual related documents, D-RAG selects and exemplifies relevant knowledge for delivering dialectic explanations that, by critically weighing opposing arguments and filtering extraneous content, clearly determine the final response. We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models. Our experiments demonstrate that D-RAG significantly improves RAG approaches, requiring low-impact computational effort and providing robustness to knowledge perturbations.
Misinformation remains one of the most significant issues in the digital age. While automated fact-checking has emerged as a viable solution, most current systems are limited to evaluating factual accuracy. However, the detrimental effect of misinformation transcends simple falsehoods; it takes advantage of how individuals perceive, interpret, and emotionally react to information. This underscores the need to move beyond factuality and adopt more human-centered detection frameworks. In this survey, we explore the evolving interplay between traditional fact-checking approaches and psychological concepts such as cognitive biases, social dynamics, and emotional responses. By analyzing state-of-the-art misinformation detection systems through the lens of human psychology and behavior, we reveal critical limitations of current methods and identify opportunities for improvement. Additionally, we outline future research directions aimed at creating more robust and adaptive frameworks, such as neuro-behavioural models that integrate technological factors with the complexities of human cognition and social influence. These approaches offer promising pathways to more effectively detect and mitigate the societal harms of misinformation.